Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 947 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.0440. Min Range: -4.0440

Max Act: 4.0440. Min Act: -0.1700

Data Index: 7368472 (Open Web Text)

Max Activating Token Index: 961

Text #1

Max Range: 4.0440. Min Range: -4.0440

Max Act: 4.0069. Min Act: -0.1700

Data Index: 4506803 (Open Web Text)

Max Activating Token Index: 393

Text #2

Max Range: 4.0440. Min Range: -4.0440

Max Act: 4.0087. Min Act: -0.1700

Data Index: 695202 (Open Web Text)

Max Activating Token Index: 811

Text #3

Max Range: 4.0440. Min Range: -4.0440

Max Act: 4.0081. Min Act: -0.1700

Data Index: 6033482 (Open Web Text)

Max Activating Token Index: 101

Text #4

Max Range: 4.0440. Min Range: -4.0440

Max Act: 4.0124. Min Act: -0.1700

Data Index: 4506802 (Open Web Text)

Max Activating Token Index: 355

Text #5

Max Range: 4.0440. Min Range: -4.0440

Max Act: 3.9891. Min Act: -0.1700

Data Index: 3725294 (Open Web Text)

Max Activating Token Index: 14

Text #6

Max Range: 4.0440. Min Range: -4.0440

Max Act: 3.9713. Min Act: -0.1700

Data Index: 4506804 (Open Web Text)

Max Activating Token Index: 573

Text #7

Max Range: 4.0440. Min Range: -4.0440

Max Act: 3.9582. Min Act: -0.1700

Data Index: 5275097 (Open Web Text)

Max Activating Token Index: 619

Text #8

Max Range: 4.0440. Min Range: -4.0440

Max Act: 3.9141. Min Act: -0.1700

Data Index: 1222425 (Open Web Text)

Max Activating Token Index: 79

Text #9

Max Range: 4.0440. Min Range: -4.0440

Max Act: 3.9530. Min Act: -0.1700

Data Index: 3017502 (Open Web Text)

Max Activating Token Index: 735

Text #10

Max Range: 4.0440. Min Range: -4.0440

Max Act: 3.9301. Min Act: -0.1700

Data Index: 4506805 (Open Web Text)

Max Activating Token Index: 957

Text #11

Max Range: 4.0440. Min Range: -4.0440

Max Act: 3.8953. Min Act: -0.1700

Data Index: 8792420 (Open Web Text)

Max Activating Token Index: 955

Text #12

Max Range: 4.0440. Min Range: -4.0440

Max Act: 3.9103. Min Act: -0.1700

Data Index: 1577525 (Open Web Text)

Max Activating Token Index: 1020

Text #13

Max Range: 4.0440. Min Range: -4.0440

Max Act: 3.8872. Min Act: -0.1700

Data Index: 4220864 (Open Web Text)

Max Activating Token Index: 116

Text #14

Max Range: 4.0440. Min Range: -4.0440

Max Act: 3.8844. Min Act: -0.1700

Data Index: 5914911 (Open Web Text)

Max Activating Token Index: 185

Text #15

Max Range: 4.0440. Min Range: -4.0440

Max Act: 3.8616. Min Act: -0.1700

Data Index: 4458657 (Open Web Text)

Max Activating Token Index: 697

Text #16

Max Range: 4.0440. Min Range: -4.0440

Max Act: 3.8721. Min Act: -0.1700

Data Index: 3716147 (Open Web Text)

Max Activating Token Index: 122

Text #17

Max Range: 4.0440. Min Range: -4.0440

Max Act: 3.8555. Min Act: -0.1700

Data Index: 4724432 (Open Web Text)

Max Activating Token Index: 597

Text #18

Max Range: 4.0440. Min Range: -4.0440

Max Act: 3.8735. Min Act: -0.1700

Data Index: 1301095 (Open Web Text)

Max Activating Token Index: 918

Text #19

Max Range: 4.0440. Min Range: -4.0440

Max Act: 3.8781. Min Act: -0.1700

Data Index: 4506806 (Open Web Text)

Max Activating Token Index: 339